Descript

Descript turns a recording into a transcript and lets you edit the media by editing the text. Delete a sentence from the transcript and it is cut from the audio and video. For talk shows and interviews this is often faster than scrubbing a waveform, because you can read the episode and remove the parts that do not work.

It also removes filler words such as "um" and "you know" in bulk, includes a Studio Sound effect that cleans up voice recordings, adds captions, and can record remote guests. Its AI tools can draft show notes, suggest clips and generate a voice to fix a misspoken word, which should be used only with the speaker's permission.

Edits made from the transcript can leave rough joins, so listen through the cut before export.